Oracle Bone Script Similiar Character Screening Approach Based on Simsiam Contrastive Learning and Supervised Learning

TL;DR

This paper introduces a novel approach combining fuzzy evaluation, self-supervised ResNet-50, and supervised RepVGG learning to identify similar oracle bone script characters across different modalities, enhancing feature learning and similarity assessment.

Contribution

It presents a new integrated method for character similarity screening using combined supervised and unsupervised learning with fuzzy evaluation, tailored for oracle bone script images.

Findings

Effective enhancement of key features through preprocessing techniques.

Improved similarity detection accuracy for oracle bone characters.

Potential to assist in deciphering unknown oracle-bone inscriptions.

Abstract

This project proposes a new method that uses fuzzy comprehensive evaluation method to integrate ResNet-50 self-supervised and RepVGG supervised learning. The source image dataset HWOBC oracle is taken as input, the target image is selected, and finally the most similar image is output in turn without any manual intervention. The same feature encoding method is not used for images of different modalities. Before the model training, the image data is preprocessed, and the image is enhanced by random rotation processing, self-square graph equalization theory algorithm, and gamma transform, which effectively enhances the key feature learning. Finally, the fuzzy comprehensive evaluation method is used to combine the results of supervised training and unsupervised training, which can better solve the "most similar" problem that is difficult to quantify. At present, there are many unknown oracle-bone inscriptions waiting for us to crack. Contacting with the glyphs can provide new ideas for cracking.